From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gurudas Pai Date: Fri, 04 Oct 2013 02:16:48 +0000 Subject: Re: [PATCH v2 0/9] sparc64: Support 47-bit physical addresses. Message-Id: <524E2510.8080301@oracle.com> List-Id: References: <20130930.123130.354302574443157859.davem@davemloft.net> In-Reply-To: <20130930.123130.354302574443157859.davem@davemloft.net> MIME-Version: 1.0 Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: sparclinux@vger.kernel.org On 10/03/2013 07:07 PM, Gurudas Pai wrote: > On 09/30/2013 09:31 AM, David Miller wrote: >> This is a respin of the original page_offset and 64-bit page >> table changes with some minor changes and a bug fix: >> >> 1) Bob's ACKs for the first 6 patches added. >> >> 2) Don't use "UL" postfix for shift counts, there is code that >> wants those to be "int", particularly printfs in mm/mm_init.c >> that use the "%d" format specifier for SECTIONS_SHIFT. >> >> 3) Adjust VA_HOLE defines to match what the new 3-level page >> tables can actually provide. >> >> Signed-off-by: David S. Miller >> -- > On a t4-1 machine with 64gb RAM , run following testcase as > > ./a.out 10000 > > And run echo 1000000 > /proc/sys/vm/nr_hugepages couple of times. > Machine becomes unusuable. > This includes "fix generic hugetlb pte check return type." patch as > well.Oom killers and then lockups. > Will try wothout patches very soon. Same issue without 47-bit patches. thanks, -Guru